Very excited to announce two papers from the last two days! This is the last gasp of summer research before teaching prep takes over August. One paper is about the geometry of latent spaces and the other is on using category theory for inference in computational geometry... 1/n
We demo’d Amazon grasp model at RSS this year. We performed over 600 grasps over one day at roughly 80-90% SR
1. On an open item set (people gave random often adversarial items),
2. In a random scene fully outdoor throughout the day
3. On a new embodiment (different from Amazon robots).
🚨 RSS Demo Paper Alert!
Amazon needs to manipulate millions of items daily—demanding robust policies that handle (1) diverse objects in cluttered warehouses, (2) adapt across robotic embodiments, and (3) deliver high performance across thousands of sites with varying layouts.
📢 New Paper Alert! 🚀
Excited to share our latest work, "Ordered Topological Deep Learning: a Network Modeling Case Study", which shows the first state-of-the-art TDL application to a real-world scenario!
📄https://t.co/FRm6AnXs3o
A thread 🧵👇 (1/5)
🚨 New Faculty Position in AI & Data Science at @ualbany (open-rank) 🚨
Albany has a great number of excellent TDA researchers, so if you are interested in #topology and #MachineLearning, check this position out!
https://t.co/3ChcNqQbFd
(1/7) Topological machine learning is a fascinating field that promises to harness the higher-order interactions encountered in complex systems, enabling new horizons to be explored and older ones to be revisited. However, in order to drive this progress, there is a critical need for topological benchmark datasets.
Our new featured LoG2024 Meetup will be held in New Delhi, India.
Dates: 26 Nov.
Website: https://t.co/g6z5jwCwWF
The call for local meetup is still open. Do not hesitate to send us your proposal!
can AI do research-level mathematics? make conjectures? prove theorems?
there’s a moving frontier between what can and cannot be done with LLMs.
that boundary just shifted a little. this is my experience with AI proving a new theorem.
1/
❓How expressive is persistent homology (PH)?
❓Can such #topology-based learning methods be as effective as message-passing neural networks in graph #MachineLearning tasks?
➡️We (@rballeba, YT) explore this question in our updated preprint.
https://t.co/dt56Lxmrrm
🧵1/n
We show that GRIL (Generalized Rank Invariant Landscape) is a piecewise affine map and compute an explicit formula for the differential of GRIL. We use this to backpropagate gradients through GRIL computation to get an end-to-end learning layer.
Absolutely biblical skies in Tasmania at 4am this morning. I’m leaving today and knew I could not pass up this opportunity for such a large solar storm. Here’s the image. I actually had to de-saturate the colours. Clouds glowing red. Insane. Shot on Nikon. Rt appreciated
We started releasing the first chapters of our Geometric Deep Learning book and the accompanying slides from the corresponding Oxford and Cambridge courses.